Docs menu

Docs / SDKs

Use Cent AI with the OpenAI JavaScript SDK

Point the openai npm package at Cent AI from Node.js or TypeScript and read the cost of each call.

Last updated


Your setup

Fills in YOUR_API_KEY in the code on this page. The key stays in this tab: it is never sent and never saved.

Prerequisites

  • A Cent AI account with balance. See Balance.
  • An API key from Keys. It looks like cai_<secret> and is shown once.
  • Node.js with the openai package:
npm install openai

Set up the client

Use the base URL https://api.cent-ai.dev/v1 and your Cent AI key. The SDK adds /chat/completions and /responses itself.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.cent-ai.dev/v1",
  apiKey: process.env.CENT_AI_KEY,
});

The SDK also reads both values from environment variables, so code that calls new OpenAI() without options works unchanged. Replace YOUR_API_KEY with your key:

export OPENAI_BASE_URL=https://api.cent-ai.dev/v1
export OPENAI_API_KEY="YOUR_API_KEY"

Call Cent AI from your server. A key placed in browser code can be read by anyone who opens the page; see Authentication.

Send a request

Chat Completions and Responses both work with the same client. Use a model name from the models page.

const r = await client.chat.completions.create({
  model: "glm-5.3",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(r.choices[0].message.content);

Parameters such as temperature, tools and response_format are sent to the model as is. A parameter the model does not support comes back as an error from the model.

Read the cost

Cent AI adds cost to the standard usage object: the amount charged for the request in USD, as a string with 9 decimal places. The SDK does not strip extra fields, but its types do not list cost, so widen the type when you read it:

type CentUsage = { cost?: string };

const r = await client.chat.completions.create({
  model: "glm-5.3",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(r.usage?.prompt_tokens, r.usage?.completion_tokens);
console.log((r.usage as CentUsage | undefined)?.cost); // "0.000363000"

In plain JavaScript, r.usage.cost works as is. On Responses, the cost is in r.usage the same way.

Streaming

For Chat Completions, ask for usage in the stream with stream_options. The last chunk before the stream ends has an empty choices array and carries usage, including cost.

const stream = await client.chat.completions.create({
  model: "glm-5.3",
  messages: [{ role: "user", content: "Hello" }],
  stream: true,
  stream_options: { include_usage: true },
});
for await (const chunk of stream) {
  if (chunk.choices.length > 0) {
    process.stdout.write(chunk.choices[0].delta.content ?? "");
  }
  if (chunk.usage) {
    console.log("\ncost:", (chunk.usage as CentUsage).cost);
  }
}

Without stream_options.include_usage, a Chat Completions stream has no usage chunk and no cost. The charge is still recorded on the Requests page. Requests that can take longer than 100 seconds must stream; see Long streaming.

Check the request

Open the Requests page in the dashboard. Each request shows its tokens per rate, the rates used and the cost. The x-request-id response header is the same ID. To read it from the SDK:

const { data, response } = await client.chat.completions
  .create({ model: "glm-5.3", messages: [{ role: "user", content: "Hello" }] })
  .withResponse();
console.log(response.headers.get("x-request-id"));

Troubleshooting

Status and codeUsual causeWhat to do
401 invalid_api_keyWrong or revoked key, or the key is still an OPENAI_API_KEY from elsewhereCheck the key, or create a new one in Keys
402 insufficient_balanceNo balance available for this modelTop up or buy a budget pack, see Balance
403 ip_not_allowed, model_not_allowedThe key's IP or model allowlist blocks the requestChange the allowlist on the key
404 model_not_foundA model name Cent AI does not haveUse a name from GET /v1/models
404 without that codeThe base URL is missing /v1Set the base URL to https://api.cent-ai.dev/v1
429 rate_limitedOver 600 requests per minute for the keyWait for Retry-After, see Rate limits
429 key_limit_exceeded, project_budget_exceededA daily or monthly limit of the key or project was reachedRaise the limit or wait until the time in the message
501 not_available_yetAn endpoint that is not open yet, such as embeddingsUse chat models; see Errors
503 upstream_timeout or a stream that stopsThe model did not start in time, or a stream hit its maximum durationSee Stream timeout

The SDK throws OpenAI.APIError subclasses for these statuses, with status and code, and retries some of them on its own. All codes are listed in Errors.